NHGH analysis

Katrine Meldgård, Margrethe Bøe Lysø, Kristine Rosted Petersen, Enrico Leonardi and Pernille Jensen

Introduction

Diabetes Mellitus is a chronic disease.

  • Pancreas fails to produce sufficient amount of insulin.
  • The body cannot effectively utilize the insulin it generates.

Problem: More than 422 million people have diabetes and 1.5 million deaths each year are directly attributed to diabetes.

Kidney disease?

AIM of the project

Method

Data set contained X observations with X variables after cleaning

Data Wrangling

Added

Descriptive analysis

Observations: 6795
Variables (augmented): 26
Diagnosed: 914
Medicated: 607

Income vs. medication

Diagnosis effect on variables

???

PCA Analysis

  • Data
    • Non-medicated individuals
    • No observations with NA
    • Only anthropometric and biomarker measurements
  • Classes not seperated

Logistic regression model

Classification

  • Model based on parameters found by LR
  • Data
    • Non-medicated individuals
    • No observations with NA
  • ~all predicted as 0
  • AUC = 0.7750374

Discussion